Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0618. Min Range: -6.0618
Max Act: 6.0618. Min Act: -0.1700
Data Index: 8677148 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0618. Min Range: -6.0618
Max Act: 6.0305. Min Act: -0.1700
Data Index: 8032735 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.9993. Min Act: -0.1700
Data Index: 7950230 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.9993. Min Act: -0.1700
Data Index: 8178494 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.9993. Min Act: -0.1700
Data Index: 2124440 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.9055. Min Act: -0.1700
Data Index: 7595714 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.8743. Min Act: -0.1700
Data Index: 8294561 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.8743. Min Act: -0.1700
Data Index: 4905404 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.8743. Min Act: -0.1700
Data Index: 8553492 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.8430. Min Act: -0.1700
Data Index: 7960284 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.8118. Min Act: -0.1700
Data Index: 532599 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.8430. Min Act: -0.1700
Data Index: 7019690 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.8118. Min Act: -0.1700
Data Index: 84782 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.8118. Min Act: -0.1700
Data Index: 7723653 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.8430. Min Act: -0.1700
Data Index: 2654100 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.8430. Min Act: -0.1700
Data Index: 4295913 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.7805. Min Act: -0.1700
Data Index: 6846041 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.7493. Min Act: -0.1700
Data Index: 5676962 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.7805. Min Act: -0.1700
Data Index: 1807828 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0618. Min Range: -6.0618
Max Act: 5.7180. Min Act: -0.1700
Data Index: 2441201 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19